Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-32K
    6. 11299
    Prev
    Next
    INDEX
    Explanations

    attributes of architectural features and decorations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chet
    -0.16
    orgia
    -0.16
    å´İ
    -0.15
    odial
    -0.15
     sublist
    -0.15
    eshire
    -0.14
    неÑģ
    -0.14
    ÑĨвеÑĤ
    -0.14
     fiction
    -0.13
    ouri
    -0.13
    POSITIVE LOGITS
     ceiling
    0.57
     ceilings
    0.55
     Ceiling
    0.50
     поÑĤол
    0.44
     roof
    0.37
     overhead
    0.37
     ceil
    0.35
    ceil
    0.35
     vault
    0.34
    -ce
    0.33
    Activations Density 0.106%

    No Known Activations